© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 326
    Prev
    Next
    INDEX
    Explanations

    considering committing crime

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     adul
    -0.13
     Abuse
    -0.12
     abuses
    -0.11
     persec
    -0.11
    anca
    -0.10
     ensl
    -0.10
     prosecutions
    -0.10
    oplay
    -0.09
     Conc
    -0.09
     Practices
    -0.09
    POSITIVE LOGITS
     crime
    0.45
     criminal
    0.37
     Crime
    0.33
    çĬ¯ç½ª
    0.31
    crime
    0.31
    Crime
    0.29
     пÑĢеÑģÑĤÑĥп
    0.26
    riminal
    0.26
    criminal
    0.25
     criminals
    0.24
    Activations Density 0.121%

    No Known Activations